marinone94
commited on
Commit
β’
3bca5eb
1
Parent(s):
c756cf3
Training in progress, step 900
Browse files- {checkpoint-600 β checkpoint-900}/config.json +0 -0
- {checkpoint-600 β checkpoint-900}/optimizer.pt +1 -1
- {checkpoint-600 β checkpoint-900}/preprocessor_config.json +0 -0
- {checkpoint-600 β checkpoint-900}/pytorch_model.bin +1 -1
- {checkpoint-600 β checkpoint-900}/rng_state.pth +2 -2
- {checkpoint-600 β checkpoint-900}/scaler.pt +1 -1
- {checkpoint-600 β checkpoint-900}/scheduler.pt +1 -1
- {checkpoint-600 β checkpoint-900}/trainer_state.json +120 -3
- {checkpoint-600 β checkpoint-900}/training_args.bin +0 -0
- pytorch_model.bin +1 -1
{checkpoint-600 β checkpoint-900}/config.json
RENAMED
File without changes
|
{checkpoint-600 β checkpoint-900}/optimizer.pt
RENAMED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 2490337809
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:586c6f70f453bacaef539f6082450d1d6345b28afac567b5164059be9e21c0aa
|
3 |
size 2490337809
|
{checkpoint-600 β checkpoint-900}/preprocessor_config.json
RENAMED
File without changes
|
{checkpoint-600 β checkpoint-900}/pytorch_model.bin
RENAMED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1262063089
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:704e6898ee156f5080bd3c12729eab90778262ef46c752641e041495f274ba56
|
3 |
size 1262063089
|
{checkpoint-600 β checkpoint-900}/rng_state.pth
RENAMED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9eb48c4b47c267134052f2e43cc544a219534620acef82e17a3e9be9f1684520
|
3 |
+
size 14503
|
{checkpoint-600 β checkpoint-900}/scaler.pt
RENAMED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 559
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e8695f57df923e22b943b0b0f2b9cc7007008e80b53ccee275b3a35963fe67e9
|
3 |
size 559
|
{checkpoint-600 β checkpoint-900}/scheduler.pt
RENAMED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 623
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:30116330e344473afc42b675f3adc8ae4b90035dba726f931014800aa6aa5856
|
3 |
size 623
|
{checkpoint-600 β checkpoint-900}/trainer_state.json
RENAMED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
-
"epoch":
|
5 |
-
"global_step":
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
@@ -240,11 +240,128 @@
|
|
240 |
"eval_steps_per_second": 0.785,
|
241 |
"eval_wer": 1.0,
|
242 |
"step": 600
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
243 |
}
|
244 |
],
|
245 |
"max_steps": 4550,
|
246 |
"num_train_epochs": 50,
|
247 |
-
"total_flos":
|
248 |
"trial_name": null,
|
249 |
"trial_params": null
|
250 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 9.885245901639344,
|
5 |
+
"global_step": 900,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
240 |
"eval_steps_per_second": 0.785,
|
241 |
"eval_wer": 1.0,
|
242 |
"step": 600
|
243 |
+
},
|
244 |
+
{
|
245 |
+
"epoch": 6.81,
|
246 |
+
"learning_rate": 7.75e-05,
|
247 |
+
"loss": 2.9921,
|
248 |
+
"step": 620
|
249 |
+
},
|
250 |
+
{
|
251 |
+
"epoch": 7.03,
|
252 |
+
"learning_rate": 8e-05,
|
253 |
+
"loss": 3.0665,
|
254 |
+
"step": 640
|
255 |
+
},
|
256 |
+
{
|
257 |
+
"epoch": 7.25,
|
258 |
+
"learning_rate": 8.25e-05,
|
259 |
+
"loss": 2.9826,
|
260 |
+
"step": 660
|
261 |
+
},
|
262 |
+
{
|
263 |
+
"epoch": 7.47,
|
264 |
+
"learning_rate": 8.5e-05,
|
265 |
+
"loss": 2.9689,
|
266 |
+
"step": 680
|
267 |
+
},
|
268 |
+
{
|
269 |
+
"epoch": 7.69,
|
270 |
+
"learning_rate": 8.75e-05,
|
271 |
+
"loss": 2.9602,
|
272 |
+
"step": 700
|
273 |
+
},
|
274 |
+
{
|
275 |
+
"epoch": 7.69,
|
276 |
+
"eval_loss": 2.9620397090911865,
|
277 |
+
"eval_runtime": 193.5851,
|
278 |
+
"eval_samples_per_second": 25.017,
|
279 |
+
"eval_steps_per_second": 0.785,
|
280 |
+
"eval_wer": 1.0,
|
281 |
+
"step": 700
|
282 |
+
},
|
283 |
+
{
|
284 |
+
"epoch": 7.91,
|
285 |
+
"learning_rate": 8.999999999999999e-05,
|
286 |
+
"loss": 2.9639,
|
287 |
+
"step": 720
|
288 |
+
},
|
289 |
+
{
|
290 |
+
"epoch": 8.13,
|
291 |
+
"learning_rate": 9.25e-05,
|
292 |
+
"loss": 3.0215,
|
293 |
+
"step": 740
|
294 |
+
},
|
295 |
+
{
|
296 |
+
"epoch": 8.35,
|
297 |
+
"learning_rate": 9.5e-05,
|
298 |
+
"loss": 2.9454,
|
299 |
+
"step": 760
|
300 |
+
},
|
301 |
+
{
|
302 |
+
"epoch": 8.57,
|
303 |
+
"learning_rate": 9.750000000000001e-05,
|
304 |
+
"loss": 2.9239,
|
305 |
+
"step": 780
|
306 |
+
},
|
307 |
+
{
|
308 |
+
"epoch": 8.79,
|
309 |
+
"learning_rate": 0.0001,
|
310 |
+
"loss": 2.8756,
|
311 |
+
"step": 800
|
312 |
+
},
|
313 |
+
{
|
314 |
+
"epoch": 8.79,
|
315 |
+
"eval_loss": 2.7302000522613525,
|
316 |
+
"eval_runtime": 191.8065,
|
317 |
+
"eval_samples_per_second": 25.249,
|
318 |
+
"eval_steps_per_second": 0.792,
|
319 |
+
"eval_wer": 1.0,
|
320 |
+
"step": 800
|
321 |
+
},
|
322 |
+
{
|
323 |
+
"epoch": 9.01,
|
324 |
+
"learning_rate": 0.0001025,
|
325 |
+
"loss": 2.8933,
|
326 |
+
"step": 820
|
327 |
+
},
|
328 |
+
{
|
329 |
+
"epoch": 9.23,
|
330 |
+
"learning_rate": 0.000105,
|
331 |
+
"loss": 2.7318,
|
332 |
+
"step": 840
|
333 |
+
},
|
334 |
+
{
|
335 |
+
"epoch": 9.45,
|
336 |
+
"learning_rate": 0.0001075,
|
337 |
+
"loss": 2.5941,
|
338 |
+
"step": 860
|
339 |
+
},
|
340 |
+
{
|
341 |
+
"epoch": 9.67,
|
342 |
+
"learning_rate": 0.00011,
|
343 |
+
"loss": 2.4441,
|
344 |
+
"step": 880
|
345 |
+
},
|
346 |
+
{
|
347 |
+
"epoch": 9.89,
|
348 |
+
"learning_rate": 0.00011250000000000001,
|
349 |
+
"loss": 2.2931,
|
350 |
+
"step": 900
|
351 |
+
},
|
352 |
+
{
|
353 |
+
"epoch": 9.89,
|
354 |
+
"eval_loss": 1.5057899951934814,
|
355 |
+
"eval_runtime": 196.4368,
|
356 |
+
"eval_samples_per_second": 24.654,
|
357 |
+
"eval_steps_per_second": 0.774,
|
358 |
+
"eval_wer": 0.9775759296054499,
|
359 |
+
"step": 900
|
360 |
}
|
361 |
],
|
362 |
"max_steps": 4550,
|
363 |
"num_train_epochs": 50,
|
364 |
+
"total_flos": 1.3944116272848585e+19,
|
365 |
"trial_name": null,
|
366 |
"trial_params": null
|
367 |
}
|
{checkpoint-600 β checkpoint-900}/training_args.bin
RENAMED
File without changes
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1262063089
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:704e6898ee156f5080bd3c12729eab90778262ef46c752641e041495f274ba56
|
3 |
size 1262063089
|